# How to fix Mismatch in shape when using .backward() function **URL:** \ **Category:** Uncategorized\ **Created:** [October 22, 2019, 4:43am UTC](https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865 "2019-10-22T04:43:23Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![JmcginleyFAU](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/bc8723/32.png) [@JmcginleyFAU](https://discuss.pytorch.org/u/JmcginleyFAU)\ **Post date:** [October 22, 2019, 4:43am UTC](https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865/1 "2019-10-22T04:43:23Z")
This is my first time using Pytorch and I am trying to run the WGAN from [WGAN](https://github.com/jalola/improved-wgan-pytorch/blob/master/gan_train.py) When implementing my own dataset and running the provided code, I get an error on line 186 (link): ```auto 156 gen_cost = aD(fake_data) 157 gen_cost = gen_cost.mean() --> 158 gen_cost.backward(mone) 159 gen_cost = -gen_cost ``` which produces: ```auto /usr/local/lib/python3.6/dist-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph) 148 products. Defaults to ``False``. 149 """ --> 150 torch.autograd.backward(self, gradient, retain_graph, create_graph) 151 152 def register_hook(self, hook): /usr/local/lib/python3.6/dist-packages/torch/autograd/ __init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables) 91 grad_tensors = list(grad_tensors) 92 ---> 93 grad_tensors = _make_grads(tensors, grad_tensors) 94 if retain_graph is None: 95 retain_graph = create_graph /usr/local/lib/python3.6/dist-packages/torch/autograd/ __init__.py in _make_grads(outputs, grads) 27 + str(grad.shape) + " and output[" 28 + str(outputs.index(out)) + "] has a shape of " ---> 29 + str(out.shape) + ".") 30 new_grads.append(grad) 31 elif grad is None: RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]). ``` I am having a hard time understanding the relationship of gen\_cost.backward(mone) and the grad\_output and output variables. Would anyone be willing to explain this to me! Appreciate it! ---
**Author:** ![albanD](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/alband/32/215_2.png) [@albanD](https://discuss.pytorch.org/u/albanD)\ **Post date:** [October 22, 2019, 1:25pm UTC](https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865/2 "2019-10-22T13:25:08Z")
Hi, The error is not very clear but it happens because we recently introduced 0 sized Tensors. As you can see, the size mismatch is between a Tensor with 1 dimension of size 1 and a tensor with 0 dimensions that contains a single element. Could you show how `mone` is created? If it is a fixed number, it should be created as `torch.tensor(42)`. If it is created using a reduction function (like sum, mean etc), the `keepdim` argument should be set to False. ---
**Author:** ![JmcginleyFAU](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/bc8723/32.png) [@JmcginleyFAU](https://discuss.pytorch.org/u/JmcginleyFAU)\ **Post date:** [October 22, 2019, 3:01pm UTC](https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865/3 "2019-10-22T15:01:09Z")
Hello AlbanD, In the Github Repo the mone variable is created by ```auto one = torch.FloatTensor([1]) mone = one * -1 aG = aG.to(device) aD = aD.to(device) one = one.to(device) mone = mone.to(device) ``` ---
**Author:** ![albanD](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/alband/32/215_2.png) [@albanD](https://discuss.pytorch.org/u/albanD)\ **Post date:** [October 22, 2019, 5:38pm UTC](https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865/4 "2019-10-22T17:38:08Z")
You can change the `one` definition by: `one = torch.tensor(1, dtype=torch.float)` That should fix your problem 🙂